Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alebgl77/claude-inc --skill triage-ndagit clone --depth 1 https://github.com/alebgl77/claude-incWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alebgl77/claude-inc/triage-nda)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/triage-nda"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/triage-nda/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/triage-nda"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/triage-nda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01008 |
| Opus 5 | $0.00050 | $0.00504 |
| Sonnet 5 | $0.00020 | $0.00202 |
| Haiku 4.5 | $0.00010 | $0.00101 |
Grade A, and why
triage-nda scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage NDA — NDA Triage
"Fast NDA review"
Built for speed: seven screens, one verdict, ten minutes. Works on pasted NDA text or a file.
When to use
- "Can I just sign this NDA?" — the speed call
- "Sales needs this countersigned today" — deal-velocity triage
- "Is this NDA actually mutual?" — direction check
- Screening a batch of inbound NDAs before a partner event
- Confidentiality terms embedded in a larger agreement belong to
review-contract, not here
Workflow
- Ingest the NDA (pasted text or file). Confirm it is a standalone NDA; note parties, stated purpose, and our disclosure direction (mostly disclosing, mostly receiving, or both).
- Screen mutuality: obligations must run both ways if information does. One-way obligations against us while we disclose is RED territory.
- Check term and survival: an agreement term of 1-3 years and confidentiality survival of 2-5 years are standard; indefinite survival passes only for trade secrets.
- Check definition breadth: "Confidential Information" should be bounded — marked, or reasonably understood as confidential. Definitions sweeping in all business contacts or "any information disclosed by any means at any time" get flagged.
- Hunt embedded landmines: non-solicit, non-compete, exclusivity, or standstill clauses do not belong in an NDA — any one of them forces RED.
- Verify the four standard carve-outs: public knowledge, prior possession, independent development, compelled disclosure (with notice where lawful). Each missing carve-out is a YELLOW fix with insert language.
- Screen residuals and IP: a residuals clause broad enough to gut confidentiality is RED; any assignment of IP, feedback, or derivatives smuggled into an NDA is RED.
- Classify and deliver: GREEN — sign under standard delegation; YELLOW — apply the listed fixes, then sign; RED — route to full review with reasons quoted.
Output format
NDA TRIAGE — <counterparty> — <date>
Direction: <mutual / we disclose / we receive> Purpose: <one line>
VERDICT: <GREEN — sign under standard delegation | YELLOW — fix, then sign | RED — full review>
SCREENS
| Check | Result | Note |
|------------------------------------|--------|-------------------|
| Mutuality | PASS | |
| Term & survival | FLAG | <what and why> |
| Definition breadth | PASS | |
| Embedded non-solicit / non-compete | PASS | |
| Standard carve-outs (4) | FLAG | missing: <which> |
| Residuals clause | PASS | none present |
| IP assignment smuggling | PASS | none present |
FIXES (YELLOW verdicts)
1. <clause> — Quote: "<verbatim>" → Insert: "<replacement language>"
2. <clause> — Quote: "<verbatim>" → Insert: "<replacement language>"
RED REASONS (RED verdicts)
- <finding> — Quote: "<verbatim>" — why it forces full review
*Issue-spotting support, not legal advice — engage counsel for binding decisions.*
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 76 lines · 100 tokens per session scan A d02f5aa18cf9
triage-nda is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,008 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
simplify-code
Parallel 4-agent cleanup of recent code changes.
community-research-insight
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
output-dev-workflow-function
Create workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing workflow structure issues.
Pair Programming
Collaboratively design, implement, review, and refine software features with a human developer using an iterative pair programming workflow. Prioritize understanding, explicit approval, small reviewable changes, and synchronized specifications.
005-agents-installation
Use when you need to install the embedded robot agents into .github/agents, .claude/agents, .cursor/agents, or .codex/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap…